{"version":1,"type":"story","url":"https://digestai.news/story/nvidia-releases-four-open-cosmos-3-nano-models-for-world-simulation","json":"https://digestai.news/story/nvidia-releases-four-open-cosmos-3-nano-models-for-world-simulation.json","markdown":"https://digestai.news/story/nvidia-releases-four-open-cosmos-3-nano-models-for-world-simulation.md","slug":"nvidia-releases-four-open-cosmos-3-nano-models-for-world-simulation","headline":"NVIDIA releases four open Cosmos 3 Nano models for world simulation","summary":"NVIDIA has added four new open-weight models to its Cosmos 3 platform, designed for generating interactive world simulations and multi-sensor driving scenes. The models—Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer, and Cosmos3-Nano-Sim-Bimanual—each specialize in different tasks like synchronized camera/LiDAR data, photorealistic video from simulator controls, and visual predictions from robot actions. All share the same 16B-parameter base and use NVIDIA’s OpenMDW1.1 license, allowing commercial and non-commercial use without restrictions.\n\nThe models aim to address gaps in simulation environments for autonomous driving and robotics. Transfer-Auto generates multi-view driving data with variable weather and lighting, while Sim-Auto streams synchronized video and LiDAR for real-time driving simulations. Sim-Transfer turns physics simulator controls into photorealistic video, and Sim-Bimanual predicts visual outcomes from robot or camera actions. NVIDIA provides technical reports, notebooks, and open skills for inference, though users need Linux, an NVIDIA GPU, Docker, and Container Toolkit to run them. The focus now shifts to evaluating how well these models support policy learning and identifying their limitations.","keyPoints":["Four new open-weight Cosmos 3 Nano models released for interactive world simulation and driving scenarios","Models include multi-view driving data, synchronized camera/LiDAR streams, photorealistic video, and robot action prediction","All use OpenMDW1.1 license; require Linux, NVIDIA GPU, Docker, and Container Toolkit for inference"],"whyItMatters":"These models advance simulation environments for autonomous driving and robotics research by enabling richer, interactive data generation. Developers can adapt them to specific sensor setups or domains, reducing reliance on real-world testing. The open weights foster collaboration but require significant computational resources to deploy.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["NVIDIA"],"models":["Cosmos3-Nano-Transfer-Auto","Cosmos3-Nano-Sim-Auto","Cosmos3-Nano-Sim-Transfer","Cosmos3-Nano-Sim-Bimanual","Cosmos 3"],"people":[]},"firstPublishedAt":"2026-10-30T22:47:00Z","updatedAt":"2026-10-30T22:47:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"Hugging Face","title":"New NVIDIA Cosmos 3 Open Models for Interactive World Simulation","url":"https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation","publishedAt":"2026-10-30T22:47:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"NVIDIA releases four open Cosmos 3 Nano models for world simulation\", 30 October 2026, https://digestai.news/story/nvidia-releases-four-open-cosmos-3-nano-models-for-world-simulation","publisher":"Digest AI","title":"NVIDIA releases four open Cosmos 3 Nano models for world simulation","datePublished":"2026-10-30T22:47:00Z","url":"https://digestai.news/story/nvidia-releases-four-open-cosmos-3-nano-models-for-world-simulation"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}